We present the design and implementation of a new garbage collection framework that significantly generalizes existing copying collectors. The Beltway framework exploits and separates object age and incrementality. It groups objects in one or more increments on queues called belts, collects belts independently, and collects increments on a belt in first-in-first-out order. We show that Beltway configurations, selected by command line options, act and perform the same as semi-space, generational, and older-first collectors, and encompass all previous copying collectors of which we are aware.

This paper reports our experiences with a mostly-concurrent incremental garbage collector, implemented in the context of a high performance virtual machine for the Java^TM programming language. The garbage collector is based on the "mostly parallel" collection algorithm of Boehm et al., and can be used as the old generation of a generational memory system. It overloads efficient write-barrier code already generated to support generational garbage collection to also identify objects that were modified during concurrent marking. These objects must be rescanned to ensure that the concurrent marking phase marks all live objects. This algorithm minimises maximum garbage collection pause times, while having only a small impact on the average garbage collection pause time and overall execution time. We support our claims with experimental results, for both a synthetic benchmark and real programs.

General purpose garbage collectors have yet to combine short pause times with high throughput. For example, generational collectors can achieve high throughput. They have modest average pause times, but occasionally collect the whole heap and consequently incur long pauses. At the other extreme, concurrent collectors, including reference counting, attain short pause times but with significant performance penalties. This paper introduces a new hybrid collector that combines copying generational collection for the young objects and reference counting the old objects to achieve both goals. It restricts copying and reference counting to the object demographics for which they perform well. Key to our algorithm is a generalization of deferred reference counting we call Ulterior Reference Counting. Ulterior reference counting safely ignores mutations to select heap objects. We compare a generational reference counting hybrid with pure reference counting, pure marksweep, and hybrid generational mark-sweep collectors. This new collector combines excellent throughput, matching a high performance generational mark-sweep hybrid, with low maximum pause times.

Copying garbage collectors have a number of advantages over noncopying collectors, including cheap allocation and avoiding fragmentation. However, in order to provide completeness (the guarantee to reclaim each garbage object eventually), standard copying collectors require space equal to twice the size of the maximum live data for a program. We present a mark-copy collection algorithm (MC) that extends generational copying collection and significantly reduces the heap space required to run a program. MC reduces space overhead by 75–85 % compared with standard copying garbage collectors, increasing the range of applications that can use copying garbage collection. We show that when MC is given the same amount of space as a generational copying collector, it improves total execution time of Java benchmarks significantly in tight heaps, and by 5–10 % in moderate size heaps. We also compare the performance of MC with a (non-generational) mark-sweep collector and a hybrid copying/mark-sweep generational collector. We find that MC can run in heaps comparable in size to the minimum heap space required by mark-sweep. We also find that for most benchmarks MC is significantly faster than mark-sweep in small and moderate size heaps. When compared with the hybrid collector, MC improves total execution time by about 5 % for some benchmarks, partly by increasing the speed of execution of the application code.

This paper describes a new garbage collection scheme for large persistent object stores that makes efficient use of the disk and main memory. The heap is divided into partitions that are collected independently using information about inter-partition references. We present efficient techniques to maintain this information stably using auxiliary data structures in memory and the log. The result is a scheme that truly preserves the localized and scalable nature of partitioned collection. Remembering

A new garbage collection algorithm for distributed object systems, called DMOS (Distributed Mature Object Space), is presented. It is derived from two previous algorithms, MOS (Mature Object Space), sometimes called the train algorithm, and PMOS (Persistent Mature Object Space). The contribution of DMOS is that it provides the following unique combination of properties for a distributed collector: safety, completeness, non-disruptiveness, incrementality, and scalability. Furthermore, the DMOS collector is non-blocking and does not use global tracing. 1 Introduction Automatic storage management is an essential property of high level programming systems providing an error-free abstraction with which the programmer may manipulate space without regard to the inessential details of physical storage. The abstraction holds only until the store becomes full. Thus it is important for the storage management system to distinguish useful data from garbage, so that the space occupied by the garbag...

Abstract. This paper presents a new algorithm for distributed garbage collection and outlines its implementation within the Network Objects system. The algorithm is based on a reference listing scheme augmented by partial tracing in order to collect distributed garbage cycles. Our collector is designed to be exible thereby allowing e ciency, expediency and fault-tolerance to be traded against completeness. Processes may be dynamically organised into groups, according to appropriate heuristics, in order to reclaim distributed garbage cycles. Unlike previous groupbased algorithms, multiple concurrent distributed garbage collections that span groups are supported: when two collections meet they may either merge, overlap or retreat. The algorithm places no overhead on local collectors and suspends local mutators only brie y. Partial tracing of the distributed graph involves only objects thought tobe part of a garbage cycle: no collaboration with other processes is required.

The performance of automatic memory management may be improved if the policies used in allocating and collecting objects had knowledge of the lifetimes of objects. To date, approaches to the pretenuring of objects in older generations have relied on profiledriven feedback gathered from trace runs. This feedback has been used to specialize allocation sites in a program. These approaches suffer from a number of limitations. We propose an alternative that through efficient sampling of objects allows for on-line adaption of allocation sites to improve the efficiency of the memory system. In doing so, we make use of a facility already present in many collectors such as those found in Java TM virtual machines: weak references. By judiciously tracking a subset of allocated objects with weak references, we are able to gather the necessary statistics to make better object-placement decisions.

Traditional database management systems perform updates-in-place and use logs and periodic checkpointing to efficiently achieve atomicity and durability. In this Thesis we shall present a different method, Shades, for achieving atomicity and durability using a copy-on-write policy instead of updates-in-place. We shall also present index structures and the implementation of Shines, a persistent functional programming language, built on top of Shades. Shades includes real-time generational garbage collection. Real-timeness is achieved by collecting only a small part, a generation, of the database at a time. Contrary to previously presented persistent garbage collection algorithms, Shades has no need to maintain metadata (remembered sets) of intra-generation pointers on disk since the metadata can be reconstructed during recovery. This considerably reduces the amount of disk writing. In conjunction with aggressive commit grouping, efficient index structures, a design specialized to a main memory environment, and a carefully crafted implementation of Shines, we have achieved surprisingly high performance, handsomely beating commercial database management systems.

In many garbage collected systems, the mutator performs a write barrier for every pointer update. Using generational garbage collectors, we study in depth three code placement options for rememberedset write barriers: inlined, out-of-line, and partially inlined (fast path inlined, slow path out-of-line). The fast path determines if the collector needs to remember the pointer update. The slow path records the pointer in a list when necessary. Efficient implementations minimize the instructions on the fast path, and record few pointers (from 0.16 to 3 % of pointer stores in our benchmarks). We find the mutator performs best with a partially inlined barrier, by a modest 1.5 % on average over full inlining. We also study the compilation cost of write-barrier code placement. We find that partial inlining reduces the compilation cost by 20 to 25 % compared to full inlining. In the context of just-in-time compilation, the application is exposed to compiler activity. Regardless of the level of compiler activity, partial inlining consistently gives a total running time performance advantage over full inlining on the SPEC JVM98 benchmarks. When the compiler optimizes all application methods on demand and compiler load is highest, partial inlining improves total performance on average by 10.2%, and up to 18.5%.